overfitting
A common pitfall in machine learning where a model learns the training data too well, including its noise, leading to poor performance on unseen data.
- 3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction
- 3DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation
- A Closer Look at Graph Transformers: Cross-Aggregation and Beyond
- Adaptive Data Analysis for Growing Data
- Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition
- Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
- Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent
- Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
- C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models
- Causality Meets the Table: Debiasing LLMs for Faithful TableQA via Front-Door Intervention
- Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples
- Controlled Visual Hallucination via Thalamus-Driven Decoupling Network for Domain Adaptation of Black-Box Predictors
- DAAC: Discrepancy-Aware Adaptive Contrastive Learning for Medical Time series
- DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning
- DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs
- DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
- Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions
- Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery
- Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection
- Diffusion-Guided Graph Data Augmentation
- Distributional LLM-as-a-Judge
- Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
- ELDET: Early-Learning Distillation with Noisy Labels for Object Detection
- Efficient Representativeness-Aware Coreset Selection
- Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
- Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation
- Enhancing the Maximum Effective Window for Long-Term Time Series Forecasting
- Evolutionary Prediction Games
- FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning
- Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models
- GMV: A Unified and Efficient Graph Multi-View Learning Framework
- GRIP: A Graph-Based Reasoning Instruction Producer
- Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning
- GeoAda: Efficiently Finetune Geometric Diffusion Models with Equivariant Adapters
- GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
- Gradient-Guided Epsilon Constraint Method for Online Continual Learning
- Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
- Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals
- HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
- How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
- Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation
- Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
- Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale
- Learning Robust Spectral Dynamics for Temporal Domain Generalization
- Learning in Compact Spaces with Approximately Normalized Transformer
- Learning to Instruct for Visual Instruction Tuning
- Less is More: Local Intrinsic Dimensions of Contextual Language Models
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild
- Multi-Scale Finetuning for Encoder-based Time Series Foundation Models
- Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
- Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting
- OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement
- OSTAR: Optimized Statistical Text-classifier with Adversarial Resistance
- Optimization Inspired Few-Shot Adaptation for Large Language Models
- P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models
- PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series
- Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
- QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification
- Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
- Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees
- Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
- Robust Hyperbolic Learning with Curvature-Aware Optimization
- SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
- STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
- Selective Learning for Deep Time Series Forecasting
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
- SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization
- TabArena: A Living Benchmark for Machine Learning on Tabular Data
- The Leaderboard Illusion
- Time-Embedded Algorithm Unrolling for Computational MRI
- Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS Dataset
- Training the Untrainable: Introducing Inductive Bias via Representational Alignment
- UFT: Unifying Supervised and Reinforcement Fine-Tuning
- Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models
- Which Algorithms Have Tight Generalization Bounds?
- Who Reasons in the Large Language Models?
- Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training
- Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training